Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    explaining facts makes sense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாளர்கள்
    0.47
     était
    0.46
     glamour
    0.44
    soluble
    0.44
     kellett
    0.43
    傾向
    0.42
    良かった
    0.42
     víctima
    0.42
     друзей
    0.42
     whence
    0.41
    POSITIVE LOGITS
    الة
    0.43
    Thay
    0.42
     از
    0.41
    IN
    0.40
     لیے
    0.40
     ‘
    0.40
    ERCISE
    0.40
     make
    0.40
    Regulation
    0.40
     plaster
    0.39
    Act Density 0.008%

    No Known Activations